SVSGAN:
Singing Voice Separation via GAN

Please upload a song or select an example music clip (only for mp3 or wave files). Note that example music clips are not in the training set.

  • Choose one way to select music :


  • Upload Your File:


    Youtube Link:


    This demo is based on SVSGAN proposed in the following paper:
    Zhe-Cheng Fan, Yen-Lin Lai, Jyh-Shing R. Jang, "SVSGAN: Singing Voice Separation via Generative Adversarial Network," in Proc. IEEE Int. Conf. Acoust., Speech and Signal Process. (ICASSP), 2018, Calgary. [BibTeX] [Static Demo]